Intracorporeal direct measurement for localizing peripheral pulmonary nodules during thoracoscopy

Construction of a risk screening and visualization system for pulmonary nodule in physical examination population based on feature self-recognition machine learning model

Objective

To assess the effectiveness of a feature self-recognition machine learning model in screening for pulmonary nodule risk in a physical examination population and to evaluate the constructed visualization system.

Methods

We analyzed data from 4,861 individuals who underwent chest CT exams during their physical examinations at the Western Theater General Hospital of the People's Liberation Army from January 2023 to November 2023. Among them, 1,168 had positive CT reports for pulmonary nodules, while 3,693 had negative findings. We developed a machine learning model using the XGBoost algorithm and employed an improved sooty tern optimization algorithm (ISTOA) for feature selection. The significance of the selected features was evaluated through univariate analysis and multivariable logistic stepwise regression analysis. A visualization system was created to estimate the risk of developing pulmonary nodules.

Results

Multivariable analysis identified older age, smoking or passive smoking, high psychological stress within the past year, occupational exposure (e.g., air pollution at the workplace), presence of chronic lung diseases, and elevated carcinoembryonic antigen levels as significant risk factors for pulmonary nodules. The feature self-recognition machine learning model further highlighted age, smoking or passive smoking, high psychological stress, occupational exposure, chronic lung diseases, family history of lung cancer, decreased albumin levels, and elevated carcinoembryonic antigen as key predictors for early pulmonary nodule risk, demonstrating superior performance.

Conclusion

The feature self-recognition machine learning model effectively aids in the early prediction and clinical identification of pulmonary nodule risk, facilitating timely intervention and improving patient prognosis.

Missing lung nodule? Intra-operative contingency plan with O-arm imaging: a case report

Despite the availability of various modalities to locate small non-palpable pulmonary nodules during minimally invasive thoracoscopic surgery, precise lung nodule resection remains a challenge. Pre-operative localization techniques add additional time, expense, and complication rate. Intra-operative localization methods, such as ultrasound, may be a real-time solution, but challenges remain with visualizing deep parenchyma lesions and operator-dependent use. Many thoracoscopic wedge resections are performed using a combination of pre-operative imaging and intra-operative landmarks. Although usually cost and time-efficient, the problem occurs when a wedge resection is performed, and the nodule is not within the specimen. This case report describes the use of the O-arm Surgical Imaging System, a full-rotation imaging system that provides three-dimensional cone-beam imaging, in an 81-year-old male patient with a solid 8 mm left lower lobe lung nodule. After two unsuccessful wedge resections, we used the O-arm and finally resected the nodule with a negative surgical margin. The O-arm provided instant feedback regarding the nodule status, allowing a standard thoracoscopy room to function as a hybrid operating room without the need to reposition the patient. Rather than convert to a thoracotomy, proceed to a larger resection, or experience a missed nodule, the O-arm proved to be a helpful intra-operative tool to find a missing lung nodule.

A novel localization technique for peripheral ground glass opacity using geometric parameters measured on CT images

Background

Currently no optimal localization technique has been established for localization of ground glass opacity (GGO). We aimed to introduce a localization technique using geometric localization for peripheral GGO.

Methods

We delineated the location of pulmonary GGO using geometric method which was similar with localization of a point in a spatial coordinate system. The localization technique was based on the anatomical landmarkers (ribs or intercostal spaces, capitulum costae and sternocostal joints). The geometric parameters were measured on preoperative CT images and the targeted GGO could be identified intraoperatively according to the parameters. We retrospectively collected the data of the patients with peripheral GGOs which were localized using this method and were wedge resected between June 2019 and July 2020. The efficacy and feasibility of the localization technique were assessed.

Results

There were 93 patients (male 34, median = 55 years) with 108 peripheral GGOs in the study. All the targeted GGOs were successfully wedge resected in the operative field with negative surgical margin at the first attempt. For each GGO, the localization parameters could be measured in 2–4 min (median = 3 min) on CT images before operation, and surgical resection could be completed in 5–10 min (median = 7 min). A total of 106 (98.15%) GGOs achieved sufficient resection margin. No complications and deaths occurred related to the localization and surgical procedure.

Conclusions

The localization technique can achieve satisfactory localization success rate and good safety profile. It can provide an easy-to-use alternative to localize peripheral GGO.